Image Attribution On Cub 200 2011 1
평가 지표
Deletion AUC score (ResNet-101)
Insertion AUC score (ResNet-101)
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Deletion AUC score (ResNet-101) | Insertion AUC score (ResNet-101) |
|---|---|---|
| grad-cam-visual-explanations-from-deep | 0.0810 | 0.7224 |
| less-is-more-fewer-interpretable-region-via | 0.0613 | 0.7262 |
| why-should-i-trust-you-explaining-the | 0.1070 | 0.6812 |
| rise-randomized-input-sampling-for | 0.0665 | 0.7193 |
| making-sense-of-dependence-efficient-black | 0.0647 | 0.6843 |
| axiomatic-attribution-for-deep-networks | 0.0728 | 0.0422 |
| deep-inside-convolutional-networks | 0.0682 | 0.6585 |
| a-unified-approach-to-interpreting-model | 0.1016 | 0.6763 |